公开(公告)号：US20210027074A1

公开(公告)日：2021-01-28

申请号：US17039215

申请日：2020-09-30

Applicant: DENSO CORPORATION

Inventor： Kunihiko CHIBA ,  Kentaro TESHIMA ,  Yusuke SEKIKAWA ,  Koichiro SUZUKI

IPC: G06K9/00 ,  G05D1/02 ,  G06T7/50

Abstract: In a vehicle system, a space area estimation method, or a space area estimation apparatus, an outside of a vehicle is captured, and an image is generated. An object causing a blind angle in the image is recognized. A depth of the recognized object is estimated. An inside of a blind angle area formed by the object is estimated.

公开(公告)号：US20200031341A1

公开(公告)日：2020-01-30

申请号：US16337031

申请日：2017-09-27

Applicant: DENSO CORPORATION

Inventor： Takayuki KITAMURA ,  Naotsugu SHIMIZU ,  Koichiro SUZUKI

IPC: B60W30/095 ,  B60W40/10 ,  G06K9/00 ,  G08G1/16

Abstract: An other lane monitoring device of the present disclosure includes an other vehicle acquisition section, a path acquisition section, a lane estimation section, and a position estimation section. The other vehicle acquisition section is configured to acquire other vehicle position information that indicates the current position of an other vehicle near the own vehicle. The path acquisition section is configured to acquire an own vehicle travel path that indicates a path along which the own vehicle has traveled. The lane estimation section is configured to use the own vehicle travel path as a basis for estimating an other lane area that is a lane where the other lane is present, the other lane being different from an own lane where the own vehicle is present. The position estimation section is configured to estimate a future position of the other vehicle indicated by the other vehicle position information, assuming that the other vehicle moves along the own vehicle travel path or in the other lane area.

公开(公告)号：US20190242987A1

公开(公告)日：2019-08-08

申请号：US16307601

申请日：2017-06-07

Applicant: DENSO CORPORATION

Inventor： Mai SAKAMOTO ,  Koichiro SUZUKI

IPC: G01S13/34 ,  G01S13/60 ,  G01S7/35 ,  G01S13/87 ,  G01S13/93

CPC classification number: G01S13/34 ,  G01S7/32 ,  G01S7/354 ,  G01S13/60 ,  G01S13/87 ,  G01S13/93 ,  G01S13/931 ,  G01S2013/9378

Abstract: A radar device calculates positions and relative velocities of points of reflection from an FMCW beat signal, extracts stationary reflection points each being a point of reflection having a relative velocity of zero, and sets, for each of the stationary reflection points, an object area estimated to contain an object including the stationary reflection point. The radar device calculates positions and relative velocities of points of reflection from a 2CW beat signal from which a DC component has been removed, extracts in-area reflection points each being a point of reflection that belongs to the object area. The radar device then computes, for each of the in-area reflection points, a cross velocity that is a velocity of the in-area reflection point in a cross-range direction, and statistically processes calculated cross velocities for each of the object areas. The radar device calculates an estimated value of a cross velocity of an object.

公开(公告)号：US20230417895A1

公开(公告)日：2023-12-28

申请号：US18463967

申请日：2023-09-08

Applicant: DENSO CORPORATION

Inventor： Koichiro SUZUKI ,  Chiharu YAMANO ,  Toshiyuki MIYAZAKI ,  Norikazu IKOMA

IPC: G01S13/58 ,  G01S13/66 ,  G01S7/40

CPC classification number: G01S13/58 ,  G01S13/66 ,  G01S7/40

Abstract: A target object is tracked based on dimensional information of an observation space including a relative velocity of the target object with respect to a sensing device for observing a reflection wave from the target object. An estimation state is acquired by estimating a state of the target object at a specific time. A reflection source of the reflection wave that gives an observation point observed at the specific time is assumed with respect to the estimation state. A state validity of the estimation state is acquired. The estimation state is updated based on the state validity expressed including a difference between dimensional information of the reflection source projected onto the observation space in the estimation state and the observation information.

公开(公告)号：US20220236401A1

公开(公告)日：2022-07-28

申请号：US17659307

申请日：2022-04-14

Applicant: DENSO CORPORATION

Inventor： Mitsutoshi MORINAGA ,  Koichiro SUZUKI ,  Chiharu YAMANO ,  Norikazu IKOMA

IPC: G01S13/72 ,  G01S17/58 ,  G01S13/42

Abstract: A tracking apparatus which tracks a target includes a predilection unit, correction unit, and updating unit. The prediction unit predicts the state distribution of the target at a specific time. The correction unit, for at least one observation point of the target, that is observed at the specific time, uses a likelihood function to define a degree of certainty of the state distribution predicted by the prediction unit, and corrects the likelihood function depending on the number of observation points. The updating unit updates the state distribution at the specific time based on the likelihood function corrected by the correction unit.

公开(公告)号：US20210081681A1

公开(公告)日：2021-03-18

申请号：US17105148

申请日：2020-11-25

Applicant: DENSO CORPORATION

Inventor： Kunihiko CHIBA ,  Yusuke SEKIKAWA ,  Koichiro SUZUKI

IPC: G06K9/00 ,  G06K9/66

Abstract: An object model learning method includes: in an object identification model forming a convolutional neural network and a warp structure warping a feature map extracted in the convolutional neural network to a different coordinate system, preparing, in the warp structure, a warp parameter for relating a position in the different coordinate system to a position in a coordinate system before warp; and learning the warp parameter to input a capture image in which an object is captured to the object identification model and output a viewpoint conversion map in which the object is identified in the different coordinate system.